Your Daily AI Research tl;dr — 2022–07–07 🧠

Portrait stylization, bias in transfer learning and Meta’s new model.

Welcome to your official daily AI research tl;dr (often with code and news) for AI enthusiasts where I share the most exciting papers I find daily, along with a one-liner summary to help you quickly determine if the article (and code) is worth investigating. I will also take this opportunity to share daily exciting news in the field.

Let’s get started with this iteration!

1️⃣ When does Bias Transfer in Transfer Learning?

This work investigates the downfall of using transfer learning (bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class), which is important to consider, especially for models released in production for real-world applications.

Link to the paper: https://arxiv.org/abs/2207.02842

2️⃣ DCT-Net: Domain-Calibrated Translation for Portrait Stylization

DCT-Net, a novel image translation architecture for few-shot portrait stylization: producing high-quality style transfer results with advanced ability to synthesize high-fidelity contents and strong…